TKTatiana Ivanovna Kuzmina

Tatiana Ivanovna Kuzmina

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tatiana Ivanovna Kuzmina has a total of 62 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Bank Resilience and The Application of Generative Artificial General Intelligence Systems in Finance and the Digital Economy

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, Yu. O. Yurova, S. A. Krashchenko, N. A. Popov, M. A. Petrova

    The article considers the theoretical aspects of digitalization of the Russian banking system and the development of fi nancial technologies of the knowledge economy based on artificial intelligence systems. The relevance of the study lies in the fact that in the context of increasing digitalization, there is a dynamic growth in the use of artificial intelligence systems, including in the banking sector, which largely contributes to its sustainable development. The novelty lies in the fact that the conducted study proposes an original approach in which, based on the ontological model, the following classes were identified representing parameters reflecting the performance of banking activities: 1) bank assets (Bank_assets); 2) net profi t (Net_profit); 3) return on equity (ROE); 4) cost of risk (Cost_of_risk); 5) non-performing loans (Non-performing_loans). At the same time, hierarchies, objects, relationships between objects and criteria were defined, which made it possible to use the obtained data in the following model of the "AI system genetic algorithm" in order to optimize the stability of the banking system. During the study, the Forbes sustainability rating of the eleven largest Russian banks in 2025 was reformatted using a correlation model, allowing for the calculation of the Financial Sustainability Ratio, which was obtained by normalization (placing it in the range from 0 to 100). The practical significance is that the resulting generational evolution allowed for an increase in the Average Sustainability indicator from 1.557 in Generation 1 to 2.107 in Generation 30. The average improved bank sustainability increased to 54.2.

  • Sustainable Development of the Regional Economy and Banking System in the Context of Digitalization and Market Uncertainty

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, A. A. Polozhenets, A. V. Sycheva, O. A. Golodova, N. N. Simonova

    This article examines the sustainable development of regional economies and regional banking systems, as they interact in the face of market uncertainty and digital transformation. The relevance of this study lies in the increased attention paid by scholars and experts to the sustainable development of regional economies and banking systems amid digital transformations in all spheres of activity, market uncertainty, and risk. The research’s scientific novelty lies in its identification of a relationship between the number of commercial bank branch offices in regions and the regional GRP. A neural network model, the "Kohonen Map", was developed for regional bank development, enabling clustering of regions. A hypothesis was put forward and proven that a forecast of bank sustainability ratios can be obtained using the developed «Random Forest» deep learning model. Using the "Random Forest" deep learning model based on artificial intelligence, an equation was derived for the relationship between the factorial and outcome features included in the model for forecasting the normalized sustainability ratio of commercial banks. A forecast of Sberbank’s sustainability ratio was obtained for three scenarios. The projected value of Sber’s stability coefficient for the first option was 0.780, falling to 0.87 % of the actual value of 0.95 in 2024. For the second option, it will be 0.859, falling to 0.94 % of the actual value of 0.95 in 2024. For the third option, it will be 0.956, which is an increase of 0.63 % to the actual value of 0.95 in 2024.

  • Digital Transformation of the Banking Sector Based on Neuro-Multiagency Systems for Sustainable Development of the Data Economy

    by N. I. Lomakin, O. A. Minaeva, M. S. Maramygin, T. I. Kuzmina, A. A. Polozencev

    This article examines theoretical aspects related to the digital transformation of the banking sector through the use of neuro-multiagent systems to ensure sustainable development. The relevance of this study lies in the widespread use of artificial intelligence (AI) and multi-agent systems across all sectors, including business, fi nance, and banking, during the implementation of the National Project "Data Economy and Digital Transformation of the State", which largely creates certain prerequisites for the sustainable development of the banking system and the data economy. The novelty of this study lies in the development of a multi-agent system that enables the collection and processing of information reflecting the activities of commercial banks, generating data suitable for subsequent use, in particular, for identifying patterns for sustainable development. The aim of the study is to develop an artificial intelligence algorithm based on the n8n service as a multi-agent system that will enable the creation of a dataset for calculating normalized fi nancial stability ratios for commercial banks. To achieve this goal, the following tasks were set and solved: identify development trends and potential applications of Large Language Models (LLMs), which are large language models implemented on the n8n service within a multi-agent system; develop a design and build a working prototype of an AI bot in n8n for processing data in the cloud service; and calculate normalized fi nancial stability ratios for commercial banks based on the collected data.

  • Forecasting OFZ26225 Bond Yield Using AI Depending on the Dynamics of the Central Bank’s Key Rate

    by N. I. Lomakin, O. A. Minaeva, M. S. Maramygin, T. I. Kuzmina, A. A. Polozencev, E. V. Kosobokova, M. V. Gogoleva

    The relevance of the study is that in modern conditions it is important to forecast the price of the OFZ bond using artificial intelligence (AI) depending on the dynamics of the Central Bank’s key rate and other factors. The forecast can be obtained using the deep learning model (DL-model) "Random Forest", which determines the practical significance of the results obtained. Scientific novelty consists in trying to prove or disprove the hypothesis that based on the use of the DL-model "Random Forest", it is possible to obtain a forecast of the yield of the OFZ bond 26225 based on the dynamics of the Central Bank’s key rate and other factors. To achieve the goal, the following tasks were set and solved: to consider the theoretical aspects of using bonds as important fi nancial instruments; to identify trends in the development of AI systems in exchange trading and the fi nancial sector; to form a forecast of the yield of the OFZ bond 26225 depending on the dynamics of the Central Bank’s key rate. The DL-model "Random Forest" was developed in Python in the Collab cloud environment. The practical significance is that the results of the study can be recommended for use in practice to provide support for management decision-making by private and corporate investors.

  • Bank Resilience and the Application of Generative Artificial General Intelligence Systems in Finance and the Digital Economy

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, A. A. Polozencev, C. E. Alifanov, G. I. Lukyanov, M. V. Pesterev

    The article considers the theoretical foundations of using multi-agent AI systems for sustainable development of the banking sector. The relevance of the study is that in modern conditions there are rapid qualitative changes and large-scale growth in the use of multi-agent systems on artificial intelligence in all areas of activity, including banking, which largely determines the sustainable development of the banking system. The novelty lies in the fact that the study proposed an approach based on an ontological model, which used such parameters of the bank’s performance as: 1) asset quality (growth); 2) liquidity; 3) profitability (ROE); 4) ESG parameter; 5) capital adequacy; 6) overdue loans, % which made it possible to calculate the "Financial Stability Ratio", which was obtained as a result of normalization (placing in the interval from 0 to 1) of some values obtained as the geometric mean of the quantities included in the model. The use of the deep learning model based on the AI "Random Forest" made it possible to obtain an equation that describes the relationship between the factorial and result features included in the model in order to obtain a predicted value of the financial stability coefficient of commercial banks for the next year. The practical significance is that the developed voice bot in the format of a multi-agent system on artificial intelligence can be successfully implemented in a commercial bank, replacing human labor, ensuring a reduction in operating costs, increasing the efficiency of banking products and services by increasing sales due to higher productivity.

  • Transition to "Humanless Business Models" in Banking as a Trend in Multiagentic AI Systems for Sustainable Development

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, A. A. Polozencev, I. A. Samorodova, I. N. Lomakin, N. N. Simonova

    The article discusses the theoretical foundations of using multi-agent AI systems for sustainable development of the banking sector. The relevance of the study is that in modern conditions there are rapid qualitative changes and large-scale growth in the use of multi-agent systems on artificial intelligence in all areas of activity, including banking, which largely determines the sustainable development of the banking system. The novelty lies in the fact that the study proposes an approach to forming a voice bot — a multi-agent system on artificial intelligence, which acts as a seller, is launched by the client in Telegram by pressing a button, freely conducts a conversation with a potential client by voice, asking and receiving answers to the required questions, forming a sales funnel from the list of "hot clients", ensuring an increase in productivity in the execution of business processes by 40 % or more. The practical significance is that the developed voice bot in the format of a multi-agent system based on artificial intelligence can be successfully implemented in a commercial bank, replacing human labor, ensuring a reduction in operating costs, increasing the efficiency of banking products and services by increasing sales due to higher productivity.

  • A Methodological Approach to Forecasting the Stability of Commercial Banks by An Ai-System in The Context of Deepening Social Inequality

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, E. A. Radionova, O. V. Yurova, Yu. V. Vertakova, A. A. Polozhentsev

    The article considers a methodological approach to forecasting the stability of commercial banks in the context of deepening social inequality. The relevance lies in the fact that in modern conditions, which are characterized by further differentiation of the population in terms of income, increasing market uncertainty and risk, the issues of sustainable development of the banking sector require further research. It should be noted that this increases the risks of reducing the effectiveness of banking activities. Maintaining the banking sector is the most important task of the country’s national security. The scientific novelty lies in the fact that the study hypothesized that the forecast of the assets of the banking system for the next month can be formed based on the use of the DL Random Forest Regression deep learning model, which uses data from the Gini coefficient variation series, the assets of commercial banks, as well as a number of macroeconomic indicators over a number of years. The process of «impoverishment» of the population can largely lead to a decrease in the growth rate of the banking sector. It is important to identify the optimal level of the Gini coefficient. The result obtained is an increment of scientific knowledge, and can be used as a methodological approach based on the use of artificial intelligence to ensure the sustainable development of commercial banks, which determines its practical significance. The purpose of the study is to use the dynamics of the Gini coefficient, which reflects the process of stratification of the population by income level, as well as a number of macroeconomic indicators to obtain a forecast of the asset value of commercial banks for the next year, using the developed AI model DL Random Forest. In the course of the research, the following tasks were set and solved to achieve the goal: to study the theoretical aspects of the stability of commercial banks, to develop a dataset of the AI model DL Random Forest, to generate a forecast value of the assets of the banking system for the next year. The neural network showed high forecast accuracy/

  • Expansion of Methodological Approaches to Assessing the Stability of Commercial Banks by Artifi cial Intelligence Systems

    by N. I. Lomakin, M. S. Maramygin, T. I. Kuzmina, E. A. Radionova, E. A. Fadeeva, Yu. V. Vertakova, N. A. Keda, S. V. Starikov, N. N. Kosinova

    The article considers the issues of sustainable development of commercial banks taking into account compliance with the ESG principles of the green economy. The relevance is that in modern conditions, which are characterized by market uncertainty and increasing risk, some aspects of the problem of sustainable development of the banking sector require additional scientific research. The scientific novelty is that the study puts forward a hypothesis that the forecast of the value of Sberbank’s assets for the next month can be formed based on the use of the DL deep learning model Random Forest Regression, which used monthly data on the volatility of shares of a number of commercial banks for 2024. The obtained result contains an increase in scientific knowledge and can be used as a methodological approach using artificial intelligence to assess the sustainability of commercial banks, which determines its practical significance. The purpose of the study is to obtain a forecast of the value of Sberbank’s assets for the next month, applying the developed DL model Random Forest Regression, using the identified patterns between changes in stock prices of a number of commercial banks, as well as their volatility. To achieve the goal, the following tasks were set and solved: to study the theoretical aspects of sustainable development of commercial banks, to develop a dataset of the DL-model "Random Forest", to form a forecast value of the result feature — the value of Sber’s assets for the next month. The neural network showed high forecast accuracy.

  • Assessment of Socio-Economic and Environmental Effects of Increasing Energy Efficiency: Global Experience

    by T. I. Kuzmina, L. L. Razumnova, N. P. Savina

    The article is devoted to the study of the problems of improving the energy efficiency of the economy and its positive impact on the economies of individual countries and a more efficient distribution of energy resources throughout the global economy. The advantages of energy efficiency using traditional sources of generation (saving energy, reducing the cost of operating and maintenance equipment, reducing excess capacity, reducing energy transmission losses, improving the reliability and safety of energy systems, etc.), as well as from the perspective of increasing the sustainability of energy services (reducing the impact on climate change, reducing environmental stress and improving the anthropogenic situation) are considered. in the regions of energy generation). The economic benefits of energy efficiency are substantiated: GDP growth, job creation, lower energy prices, energy poverty, and improved trade balance. Based on the analysis of energy consumption and energy efficiency of the GDP of the countries of the world, the leading countries (Curacao, Venezuela, Guyana, Ireland, Djibouti, etc.) and outsider countries (Republic of Korea, Macao, Congo, Maldives, Tonga, etc.) were identified in terms of the rate of reduction of the energy intensity of the economy. It has been revealed that the main trend in energy efficiency for investors and other stakeholders in the foreseeable future will be to increase the energy efficiency of buildings and increase the pace of their reconstruction; decarbonization of heating and cooling systems, accompanied by changes in building codes, energy efficiency standards for household appliances and heating and cooling technologies. It is noted that the lack of a physically tangible benefit hinders the growth of investments in energy efficiency; difficulties in reliably predicting the result, measuring energy savings and non-energy benefits (ecology, comfort level, etc.) and quantifying it. The methodological issues of evaluating energy efficiency improvement projects, including the effects of monitoring and verifi cation, are nvestigated.

  • Methodological Foundations of The Paradigm of Digital Sustainability and Risk of The Banking System Based on The Use of Options (рart 2)

    by N. I. Lomakin, T. I. Kuzmina, M. S. Maramygin, E. A. Fadeeva, V. V. Pokidova, N. T. Shabanov, Ya. A. Popova

    The article considers the theoretical foundations of the sustainability of the domestic banking system in the context of digitalization and increasing market uncertainty. The relevance of the study is due to the fact that in modern conditions there is a further increase in the scale of use of high-performance artificial intelligence systems. The scientific novelty lies in the fact that the study puts forward and proves the hypothesis that with the help of the artificial intelligence system DL-model «Random Forest» an accurate forecast of the closing price of Sberbank shares can be obtained, and also explores approaches aimed at filling the gap in theoretical issues related to modeling the mechanism for ensuring the sustainability of the banking system using options. The practical significance is that the results can be recommended for use in practice. The work used such research methods as statistical, monographic, analytical, the deep learning model «Random Forest» based on its method «DecisionTreeRegressor» (Decision Tree Regression), methods for constructing histograms in the Collab service, as well as Python libraries: pandas, sklearn and others. The neural network model included parameters reflecting the development of the banking system for the period from January 2016 to July 2024. The model showed good forecasting accuracy, so the forecast for November 1, 2024 was 272.07 rubles, with the actual value of the price of an ordinary share of Sberbank of 255.98 rubles. The forecast error was 16.03 rubles, or 5.91 % of the actual price. At the same time, the average absolute error was 11.64.